Python tf_grouping.knn_point() Examples
The following are 27
code examples of tf_grouping.knn_point().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
tf_grouping
, or try the search function
.
.
Example #1
| Source File: net_utils.py From meteornet with MIT License | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
sample_idx = farthest_point_sample(npoint, xyz)
new_xyz = gather_point(xyz, sample_idx) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, sample_idx, grouped_xyz
Example #2
| Source File: pointnet_util.py From path_invariance_map_network with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #3
| Source File: pointnet_util.py From frustum-pointnets with Apache License 2.0 | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #4
| Source File: pointnet_util.py From flownet3d with MIT License | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #5
| Source File: pointnet_util.py From JSNet with MIT License | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_, idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1, 1, nsample, 1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #6
| Source File: tf_util.py From scanobjectnn with MIT License | 5 votes |
|
def pc_sampling(xyz,
feat,
nsample,
num_point,
scope='sampling'):
""" Fully connected layer with non-linear operation.
Args:
xyz: 3-D tensor B x N x 3
nsample: k
num_point: N2
feat: 3-D tensor B x N x C
Returns:
feat_sample: 3-D tensor B x N2 x C
"""
with tf.variable_scope(scope) as sc:
xyz_new = gather_point(xyz, farthest_point_sample(num_point, xyz))
_, idx_pooling = knn_point(nsample, xyz, xyz_new)
grouped_points = group_point(feat, idx_pooling)
feat_sample = tf.nn.max_pool(grouped_points, [1,1,nsample,1], [1,1,1,1],
padding='VALID', data_format='NHWC', name="MAX_POOLING")
feat_sample = tf.squeeze(feat_sample, axis=[2])
return feat_sample, xyz_new
Example #7
| Source File: pointnet_util.py From scanobjectnn with MIT License | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #8
| Source File: pointnet_util.py From dfc2019 with MIT License | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #9
| Source File: pointnet_util.py From reading-frustum-pointnets-code with Apache License 2.0 | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #10
| Source File: pointnet_util.py From SGPN with MIT License | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, tnet_spec=None, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
tnet_spec: dict (keys: mlp, mlp2, is_training, bn_decay), if None do not apply tnet
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if tnet_spec is not None:
grouped_xyz = tnet(grouped_xyz, tnet_spec)
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #11
| Source File: pointnet_util.py From GSPN with MIT License | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, tnet_spec=None, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
tnet_spec: dict (keys: mlp, mlp2, is_training, bn_decay), if None do not apply tnet
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if tnet_spec is not None:
grouped_xyz = tnet(grouped_xyz, tnet_spec)
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #12
| Source File: tf_util.py From SpiderCNN with MIT License | 5 votes |
|
def pc_sampling(xyz,
feat,
nsample,
num_point,
scope='sampling'):
""" Fully connected layer with non-linear operation.
Args:
xyz: 3-D tensor B x N x 3
nsample: k
num_point: N2
feat: 3-D tensor B x N x C
Returns:
feat_sample: 3-D tensor B x N2 x C
"""
with tf.variable_scope(scope) as sc:
xyz_new = gather_point(xyz, farthest_point_sample(num_point, xyz))
_, idx_pooling = knn_point(nsample, xyz, xyz_new)
grouped_points = group_point(feat, idx_pooling)
feat_sample = tf.nn.max_pool(grouped_points, [1,1,nsample,1], [1,1,1,1],
padding='VALID', data_format='NHWC', name="MAX_POOLING")
feat_sample = tf.squeeze(feat_sample, axis=[2])
return feat_sample, xyz_new
Example #13
| Source File: pointnet_util.py From Geo-CNN with Apache License 2.0 | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #14
| Source File: geoconv_util.py From Geo-CNN with Apache License 2.0 | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #15
| Source File: pointnet_util.py From SPFN with MIT License | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #16
| Source File: pointnet2.py From PointRNN with MIT License | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs (subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #17
| Source File: pointnet_util.py From ASIS with MIT License | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #18
| Source File: pointnet_util.py From deep-functional-dictionaries with MIT License | 5 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
Example #19
| Source File: spidercnn_cls_xyz.py From SpiderCNN with MIT License | 4 votes |
|
def get_model(xyz, is_training, bn_decay=None, num_classes=40):
batch_size = xyz.get_shape()[0].value
num_point = xyz.get_shape()[1].value
nsample = 20
G = 16
taylor_channel = 5
with tf.variable_scope('delta') as sc:
_, idx = knn_point(nsample, xyz, xyz)
grouped_xyz = group_point(xyz, idx)
point_cloud_tile = tf.expand_dims(xyz, [2])
point_cloud_tile = tf.tile(point_cloud_tile, [1, 1, nsample, 1])
delta = grouped_xyz - point_cloud_tile
with tf.variable_scope('fanConv1') as sc:
feat_1 = tf_util.spiderConv(xyz, idx, delta, 32, taylor_channel = taylor_channel,
gn=True, G=G, is_multi_GPU=True)
with tf.variable_scope('fanConv2') as sc:
feat_2 = tf_util.spiderConv(feat_1, idx, delta, 64, taylor_channel = taylor_channel,
gn=True, G=G, is_multi_GPU=True)
with tf.variable_scope('fanConv3') as sc:
feat_3 = tf_util.spiderConv(feat_2, idx, delta, 128, taylor_channel = taylor_channel,
gn=True, G=G, is_multi_GPU=True)
with tf.variable_scope('fanConv4') as sc:
feat_4 = tf_util.spiderConv(feat_3, idx, delta, 256, taylor_channel = taylor_channel,
gn=True, G=G, is_multi_GPU=True)
feat = tf.concat([feat_1, feat_2, feat_3, feat_4], 2)
#top-k pooling
net = tf_util.topk_pool(feat, k = 2, scope='topk_pool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 1024, bn=True, is_training=is_training,
scope='fc1', bn_decay=bn_decay, is_multi_GPU=True)
net = tf_util.dropout(net, keep_prob=0.3, is_training=is_training,
scope='dp1')
net = tf_util.fully_connected(net, 512, bn=True, is_training=is_training,
scope='fc2', bn_decay=bn_decay, is_multi_GPU=True)
net = tf_util.dropout(net, keep_prob=0.3, is_training=is_training,
scope='dp2')
net = tf_util.fully_connected(net, 40, activation_fn=None, scope='fc3')
return net
Example #20
| Source File: spidercnn_cls.py From SpiderCNN with MIT License | 4 votes |
|
def get_model(xyz_withnor, is_training, bn_decay=None, num_classes=40):
batch_size = xyz_withnor.get_shape()[0].value
num_point = xyz_withnor.get_shape()[1].value
K_knn = 20
taylor_channel = 3
xyz = xyz_withnor[:, :, 0:3]
with tf.variable_scope('delta') as sc:
_, idx = knn_point(K_knn, xyz, xyz)
grouped_xyz = group_point(xyz, idx)
point_cloud_tile = tf.expand_dims(xyz, [2])
point_cloud_tile = tf.tile(point_cloud_tile, [1, 1, K_knn, 1])
delta = grouped_xyz - point_cloud_tile
with tf.variable_scope('SpiderConv1') as sc:
feat_1 = tf_util.spiderConv(xyz_withnor, idx, delta, 32, taylor_channel = taylor_channel,
bn=True, is_training=is_training, bn_decay=bn_decay)
with tf.variable_scope('SpiderConv2') as sc:
feat_2 = tf_util.spiderConv(feat_1, idx, delta, 64, taylor_channel = taylor_channel,
bn=True, is_training=is_training, bn_decay=bn_decay)
with tf.variable_scope('SpiderConv3') as sc:
feat_3 = tf_util.spiderConv(feat_2, idx, delta, 128, taylor_channel = taylor_channel,
bn=True, is_training=is_training, bn_decay=bn_decay)
with tf.variable_scope('SpiderConv4') as sc:
feat_4 = tf_util.spiderConv(feat_3, idx, delta, 256, taylor_channel = taylor_channel,
bn=True, is_training=is_training, bn_decay=bn_decay)
feat = tf.concat([feat_1, feat_2, feat_3, feat_4], 2)
#top-k pooling
net = tf_util.topk_pool(feat, k = 2, scope='topk_pool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 512, bn=True, is_training=is_training,
scope='fc1', bn_decay=bn_decay)
net = tf_util.dropout(net, keep_prob=0.5, is_training=is_training,
scope='dp1')
net = tf_util.fully_connected(net, 256, bn=True, is_training=is_training,
scope='fc2', bn_decay=bn_decay)
net = tf_util.dropout(net, keep_prob=0.5, is_training=is_training,
scope='dp2')
net = tf_util.fully_connected(net, 40, activation_fn=None, scope='fc3')
return net
Example #21
| Source File: pointrnn_cell_impl.py From PointRNN with MIT License | 4 votes |
|
def point_rnn(P1,
P2,
X1,
S2,
radius,
nsample,
out_channels,
knn=False,
pooling='max',
scope='point_rnn'):
"""
Input:
P1: (batch_size, npoint, 3)
P2: (batch_size, npoint, 3)
X1: (batch_size, npoint, feat_channels)
S2: (batch_size, npoint, out_channels)
Output:
S1: (batch_size, npoint, out_channels)
"""
# 1. Sample points
if knn:
_, idx = knn_point(nsample, P2, P1)
else:
idx, cnt = query_ball_point(radius, nsample, P2, P1)
_, idx_knn = knn_point(nsample, P2, P1)
cnt = tf.tile(tf.expand_dims(cnt, -1), [1, 1, nsample])
idx = tf.where(cnt > (nsample-1), idx, idx_knn)
# 2.1 Group P2 points
P2_grouped = group_point(P2, idx) # batch_size, npoint, nsample, 3
# 2.2 Group P2 states
S2_grouped = group_point(S2, idx) # batch_size, npoint, nsample, out_channels
# 3. Calcaulate displacements
P1_expanded = tf.expand_dims(P1, 2) # batch_size, npoint, 1, 3
displacement = P2_grouped - P1_expanded # batch_size, npoint, nsample, 3
# 4. Concatenate X1, S2 and displacement
if X1 is not None:
X1_expanded = tf.tile(tf.expand_dims(X1, 2), [1, 1, nsample, 1]) # batch_size, npoint, sample, feat_channels
correlation = tf.concat([S2_grouped, X1_expanded], axis=3) # batch_size, npoint, nsample, feat_channels+out_channels
correlation = tf.concat([correlation, displacement], axis=3) # batch_size, npoint, nsample, feat_channels+out_channels+3
else:
correlation = tf.concat([S2_grouped, displacement], axis=3) # batch_size, npoint, nsample, out_channels+3
# 5. Fully-connected layer (the only parameters)
with tf.variable_scope(scope) as sc:
S1 = tf.layers.conv2d(inputs=correlation, filters=out_channels, kernel_size=1, strides=1, padding='valid', data_format='channels_last', activation=None, name='fc')
# 6. Pooling
if pooling=='max':
return tf.reduce_max(S1, axis=[2], keepdims=False)
elif pooling=='avg':
return tf.reduce_mean(S1, axis=[2], keepdims=False)
Example #22
| Source File: spidercnn_cls_xyz.py From scanobjectnn with MIT License | 4 votes |
|
def get_model(xyz, is_training, bn_decay=None, num_class=NUM_CLASSES):
batch_size = xyz.get_shape()[0].value
num_point = xyz.get_shape()[1].value
nsample = 20
G = 16
taylor_channel = 5
with tf.variable_scope('delta') as sc:
_, idx = knn_point(nsample, xyz, xyz)
grouped_xyz = group_point(xyz, idx)
point_cloud_tile = tf.expand_dims(xyz, [2])
point_cloud_tile = tf.tile(point_cloud_tile, [1, 1, nsample, 1])
delta = grouped_xyz - point_cloud_tile
with tf.variable_scope('fanConv1') as sc:
feat_1 = tf_util.spiderConv(xyz, idx, delta, 32, taylor_channel = taylor_channel,
gn=True, G=G, is_multi_GPU=True)
with tf.variable_scope('fanConv2') as sc:
feat_2 = tf_util.spiderConv(feat_1, idx, delta, 64, taylor_channel = taylor_channel,
gn=True, G=G, is_multi_GPU=True)
with tf.variable_scope('fanConv3') as sc:
feat_3 = tf_util.spiderConv(feat_2, idx, delta, 128, taylor_channel = taylor_channel,
gn=True, G=G, is_multi_GPU=True)
with tf.variable_scope('fanConv4') as sc:
feat_4 = tf_util.spiderConv(feat_3, idx, delta, 256, taylor_channel = taylor_channel,
gn=True, G=G, is_multi_GPU=True)
feat = tf.concat([feat_1, feat_2, feat_3, feat_4], 2)
#top-k pooling
net = tf_util.topk_pool(feat, k = 2, scope='topk_pool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 1024, bn=True, is_training=is_training,
scope='fc1', bn_decay=bn_decay, is_multi_GPU=True)
net = tf_util.dropout(net, keep_prob=0.3, is_training=is_training,
scope='dp1')
net = tf_util.fully_connected(net, 512, bn=True, is_training=is_training,
scope='fc2', bn_decay=bn_decay, is_multi_GPU=True)
net = tf_util.dropout(net, keep_prob=0.3, is_training=is_training,
scope='dp2')
net = tf_util.fully_connected(net, num_class, activation_fn=None, scope='fc3')
return net
Example #23
| Source File: net_utils.py From meteornet with MIT License | 4 votes |
|
def set_upconv_module(xyz1, xyz2, feat1, feat2, nsample, mlp, mlp2, is_training, scope, bn_decay=None, bn=True, pooling='max', radius=None, knn=True):
"""
Feature propagation from xyz2 (less points) to xyz1 (more points)
Inputs:
xyz1: (batch_size, npoint1, 3)
xyz2: (batch_size, npoint2, 3)
feat1: (batch_size, npoint1, channel1) features for xyz1 points (earlier layers)
feat2: (batch_size, npoint2, channel2) features for xyz2 points
Output:
feat1_new: (batch_size, npoint2, mlp[-1] or mlp2[-1] or channel1+3)
TODO: Add support for skip links. Study how delta(XYZ) plays a role in feature updating.
"""
with tf.variable_scope(scope) as sc:
if knn:
l2_dist, idx = knn_point(nsample, xyz2, xyz1)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz2, xyz1)
xyz2_grouped = group_point(xyz2, idx) # batch_size, npoint1, nsample, 3
xyz1_expanded = tf.expand_dims(xyz1, 2) # batch_size, npoint1, 1, 3
xyz_diff = xyz2_grouped - xyz1_expanded # batch_size, npoint1, nsample, 3
feat2_grouped = group_point(feat2, idx) # batch_size, npoint1, nsample, channel2
net = tf.concat([feat2_grouped, xyz_diff], axis=3) # batch_size, npoint1, nsample, channel2+3
if mlp is None: mlp=[]
for i, num_out_channel in enumerate(mlp):
net = tf_util.conv2d(net, num_out_channel, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv%d'%(i), bn_decay=bn_decay)
if pooling=='max':
feat1_new = tf.reduce_max(net, axis=[2], keep_dims=False, name='maxpool') # batch_size, npoint1, mlp[-1]
elif pooling=='avg':
feat1_new = tf.reduce_mean(net, axis=[2], keep_dims=False, name='avgpool') # batch_size, npoint1, mlp[-1]
if feat1 is not None:
feat1_new = tf.concat([feat1_new, feat1], axis=2) # batch_size, npoint1, mlp[-1]+channel1
feat1_new = tf.expand_dims(feat1_new, 2) # batch_size, npoint1, 1, mlp[-1]+channel2
if mlp2 is None: mlp2=[]
for i, num_out_channel in enumerate(mlp2):
feat1_new = tf_util.conv2d(feat1_new, num_out_channel, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='post-conv%d'%(i), bn_decay=bn_decay)
feat1_new = tf.squeeze(feat1_new, [2]) # batch_size, npoint1, mlp2[-1]
return feat1_new
Example #24
| Source File: pointnet_util.py From flownet3d with MIT License | 4 votes |
|
def flow_embedding_module(xyz1, xyz2, feat1, feat2, radius, nsample, mlp, is_training, bn_decay, scope, bn=True, pooling='max', knn=True, corr_func='elementwise_product'):
"""
Input:
xyz1: (batch_size, npoint, 3)
xyz2: (batch_size, npoint, 3)
feat1: (batch_size, npoint, channel)
feat2: (batch_size, npoint, channel)
Output:
xyz1: (batch_size, npoint, 3)
feat1_new: (batch_size, npoint, mlp[-1])
"""
if knn:
_, idx = knn_point(nsample, xyz2, xyz1)
else:
idx, cnt = query_ball_point(radius, nsample, xyz2, xyz1)
_, idx_knn = knn_point(nsample, xyz2, xyz1)
cnt = tf.tile(tf.expand_dims(cnt, -1), [1,1,nsample])
idx = tf.where(cnt > (nsample-1), idx, idx_knn)
xyz2_grouped = group_point(xyz2, idx) # batch_size, npoint, nsample, 3
xyz1_expanded = tf.expand_dims(xyz1, 2) # batch_size, npoint, 1, 3
xyz_diff = xyz2_grouped - xyz1_expanded # batch_size, npoint, nsample, 3
feat2_grouped = group_point(feat2, idx) # batch_size, npoint, nsample, channel
feat1_expanded = tf.expand_dims(feat1, 2) # batch_size, npoint, 1, channel
# TODO: change distance function
if corr_func == 'elementwise_product':
feat_diff = feat2_grouped * feat1_expanded # batch_size, npoint, nsample, channel
elif corr_func == 'concat':
feat_diff = tf.concat(axis=-1, values=[feat2_grouped, tf.tile(feat1_expanded,[1,1,nsample,1])]) # batch_size, npoint, sample, channel*2
elif corr_func == 'dot_product':
feat_diff = tf.reduce_sum(feat2_grouped * feat1_expanded, axis=[-1], keep_dims=True) # batch_size, npoint, nsample, 1
elif corr_func == 'cosine_dist':
feat2_grouped = tf.nn.l2_normalize(feat2_grouped, -1)
feat1_expanded = tf.nn.l2_normalize(feat1_expanded, -1)
feat_diff = tf.reduce_sum(feat2_grouped * feat1_expanded, axis=[-1], keep_dims=True) # batch_size, npoint, nsample, 1
elif corr_func == 'flownet_like': # assuming square patch size k = 0 as the FlowNet paper
batch_size = xyz1.get_shape()[0].value
npoint = xyz1.get_shape()[1].value
feat_diff = tf.reduce_sum(feat2_grouped * feat1_expanded, axis=[-1], keep_dims=True) # batch_size, npoint, nsample, 1
total_diff = tf.concat(axis=-1, values=[xyz_diff, feat_diff]) # batch_size, npoint, nsample, 4
feat1_new = tf.reshape(total_diff, [batch_size, npoint, -1]) # batch_size, npoint, nsample*4
#feat1_new = tf.concat(axis=[-1], values=[feat1_new, feat1]) # batch_size, npoint, nsample*4+channel
return xyz1, feat1_new
feat1_new = tf.concat([feat_diff, xyz_diff], axis=3) # batch_size, npoint, nsample, [channel or 1] + 3
# TODO: move scope to outer indent
with tf.variable_scope(scope) as sc:
for i, num_out_channel in enumerate(mlp):
feat1_new = tf_util.conv2d(feat1_new, num_out_channel, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv_diff_%d'%(i), bn_decay=bn_decay)
if pooling=='max':
feat1_new = tf.reduce_max(feat1_new, axis=[2], keep_dims=False, name='maxpool_diff')
elif pooling=='avg':
feat1_new = tf.reduce_mean(feat1_new, axis=[2], keep_dims=False, name='avgpool_diff')
return xyz1, feat1_new
Example #25
| Source File: pointnet_util.py From flownet3d with MIT License | 4 votes |
|
def set_upconv_module(xyz1, xyz2, feat1, feat2, nsample, mlp, mlp2, is_training, scope, bn_decay=None, bn=True, pooling='max', radius=None, knn=True):
"""
Feature propagation from xyz2 (less points) to xyz1 (more points)
Inputs:
xyz1: (batch_size, npoint1, 3)
xyz2: (batch_size, npoint2, 3)
feat1: (batch_size, npoint1, channel1) features for xyz1 points (earlier layers)
feat2: (batch_size, npoint2, channel2) features for xyz2 points
Output:
feat1_new: (batch_size, npoint2, mlp[-1] or mlp2[-1] or channel1+3)
TODO: Add support for skip links. Study how delta(XYZ) plays a role in feature updating.
"""
with tf.variable_scope(scope) as sc:
if knn:
l2_dist, idx = knn_point(nsample, xyz2, xyz1)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz2, xyz1)
xyz2_grouped = group_point(xyz2, idx) # batch_size, npoint1, nsample, 3
xyz1_expanded = tf.expand_dims(xyz1, 2) # batch_size, npoint1, 1, 3
xyz_diff = xyz2_grouped - xyz1_expanded # batch_size, npoint1, nsample, 3
feat2_grouped = group_point(feat2, idx) # batch_size, npoint1, nsample, channel2
net = tf.concat([feat2_grouped, xyz_diff], axis=3) # batch_size, npoint1, nsample, channel2+3
if mlp is None: mlp=[]
for i, num_out_channel in enumerate(mlp):
net = tf_util.conv2d(net, num_out_channel, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv%d'%(i), bn_decay=bn_decay)
if pooling=='max':
feat1_new = tf.reduce_max(net, axis=[2], keep_dims=False, name='maxpool') # batch_size, npoint1, mlp[-1]
elif pooling=='avg':
feat1_new = tf.reduce_mean(net, axis=[2], keep_dims=False, name='avgpool') # batch_size, npoint1, mlp[-1]
if feat1 is not None:
feat1_new = tf.concat([feat1_new, feat1], axis=2) # batch_size, npoint1, mlp[-1]+channel1
feat1_new = tf.expand_dims(feat1_new, 2) # batch_size, npoint1, 1, mlp[-1]+channel2
if mlp2 is None: mlp2=[]
for i, num_out_channel in enumerate(mlp2):
feat1_new = tf_util.conv2d(feat1_new, num_out_channel, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='post-conv%d'%(i), bn_decay=bn_decay)
feat1_new = tf.squeeze(feat1_new, [2]) # batch_size, npoint1, mlp2[-1]
return feat1_new
Example #26
| Source File: net_utils.py From meteornet with MIT License | 4 votes |
|
def flow_embedding_module(xyz1, xyz2, feat1, feat2, radius, nsample, mlp, is_training, bn_decay, scope, bn=True, pooling='max', knn=True, corr_func='elementwise_product'):
"""
Input:
xyz1: (batch_size, npoint, 3)
xyz2: (batch_size, npoint, 3)
feat1: (batch_size, npoint, channel)
feat2: (batch_size, npoint, channel)
Output:
xyz1: (batch_size, npoint, 3)
feat1_new: (batch_size, npoint, mlp[-1])
"""
if knn:
_, idx = knn_point(nsample, xyz2, xyz1)
else:
idx, cnt = query_ball_point(radius, nsample, xyz2, xyz1)
_, idx_knn = knn_point(nsample, xyz2, xyz1)
cnt = tf.tile(tf.expand_dims(cnt, -1), [1,1,nsample])
idx = tf.where(cnt > (nsample-1), idx, idx_knn)
xyz2_grouped = group_point(xyz2, idx) # batch_size, npoint, nsample, 3
xyz1_expanded = tf.expand_dims(xyz1, 2) # batch_size, npoint, 1, 3
xyz_diff = xyz2_grouped - xyz1_expanded # batch_size, npoint, nsample, 3
feat2_grouped = group_point(feat2, idx) # batch_size, npoint, nsample, channel
feat1_expanded = tf.expand_dims(feat1, 2) # batch_size, npoint, 1, channel
# TODO: change distance function
if corr_func == 'elementwise_product':
feat_diff = feat2_grouped * feat1_expanded # batch_size, npoint, nsample, channel
elif corr_func == 'concat':
feat_diff = tf.concat(axis=-1, values=[feat2_grouped, tf.tile(feat1_expanded,[1,1,nsample,1])]) # batch_size, npoint, sample, channel*2
elif corr_func == 'dot_product':
feat_diff = tf.reduce_sum(feat2_grouped * feat1_expanded, axis=[-1], keep_dims=True) # batch_size, npoint, nsample, 1
elif corr_func == 'cosine_dist':
feat2_grouped = tf.nn.l2_normalize(feat2_grouped, -1)
feat1_expanded = tf.nn.l2_normalize(feat1_expanded, -1)
feat_diff = tf.reduce_sum(feat2_grouped * feat1_expanded, axis=[-1], keep_dims=True) # batch_size, npoint, nsample, 1
elif corr_func == 'flownet_like': # assuming square patch size k = 0 as the FlowNet paper
batch_size = xyz1.get_shape()[0].value
npoint = xyz1.get_shape()[1].value
feat_diff = tf.reduce_sum(feat2_grouped * feat1_expanded, axis=[-1], keep_dims=True) # batch_size, npoint, nsample, 1
total_diff = tf.concat(axis=-1, values=[xyz_diff, feat_diff]) # batch_size, npoint, nsample, 4
feat1_new = tf.reshape(total_diff, [batch_size, npoint, -1]) # batch_size, npoint, nsample*4
#feat1_new = tf.concat(axis=[-1], values=[feat1_new, feat1]) # batch_size, npoint, nsample*4+channel
return xyz1, feat1_new
feat1_new = tf.concat([feat_diff, xyz_diff], axis=3) # batch_size, npoint, nsample, [channel or 1] + 3
# TODO: move scope to outer indent
with tf.variable_scope(scope) as sc:
for i, num_out_channel in enumerate(mlp):
feat1_new = tf_util.conv2d(feat1_new, num_out_channel, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv_diff_%d'%(i), bn_decay=bn_decay)
if pooling=='max':
feat1_new = tf.reduce_max(feat1_new, axis=[2], keep_dims=False, name='maxpool_diff')
elif pooling=='avg':
feat1_new = tf.reduce_mean(feat1_new, axis=[2], keep_dims=False, name='avgpool_diff')
return xyz1, feat1_new
Example #27
| Source File: pointnet_util.py From articulated-part-induction with MIT License | 4 votes |
|
def sample_and_group(npoint, radius, nsample, xyz, points, tnet_spec=None, knn=False, use_xyz=True, centralize_points=False):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
tnet_spec: dict (keys: mlp, mlp2, is_training, bn_decay), if None do not apply tnet
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
fpsidx = farthest_point_sample(npoint, xyz)
new_xyz = gather_point(xyz, fpsidx) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if tnet_spec is not None:
grouped_xyz = tnet(grouped_xyz, tnet_spec)
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if centralize_points:
central_points = gather_point(points[:,:,:3], fpsidx)
grouped_points = tf.concat((grouped_points[:,:,:,:3]-tf.tile(tf.expand_dims(central_points, 2), [1,1,nsample,1]),grouped_points[:,:,:,3:]),-1)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nsample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
